AMDGPU: Do not clobber SCC in SIWholeQuadMode

[arsenm]

Is WQM needed for correctness or is it just an optimization?

lib/Target/AMDGPU/SIWholeQuadMode.cpp

510–511 ↗

(On Diff #63426)

These can be combined with findRegisterUseOperandIdx

551 ↗

(On Diff #63426)

This function is kind of complicated to special case track SCC liveness. Can you use LivePhysRegs or check the LiveIntervals to simplify it (I think there was some issue with tracking physical registers with LIS last time I tried to do it, but I don't remember)

566–569 ↗

(On Diff #63426)

The Clean = true can be hoisted to the initializer

572–573 ↗

(On Diff #63426)

range loop

574 ↗

(On Diff #63426)

Maybe this should get the read operand and see if it is undef?

578–579 ↗

(On Diff #63426)

Should check if it's dead?

597 ↗

(On Diff #63426)

I think these should use MI's DebugLoc

605–606 ↗

(On Diff #63426)

Insert through LIS

609 ↗

(On Diff #63426)

This can just return Restore

621 ↗

(On Diff #63426)

Should set DebugLoc

638 ↗

(On Diff #63426)

Should set DebugLoc

675 ↗

(On Diff #63426)

Capitalize

test/CodeGen/AMDGPU/wqm.ll

423 ↗

(On Diff #63426)

I don't see check lines for the cmp + select restore pattern here. Where is the scc def? This test also probably needs a comment

429 ↗

(On Diff #63426)

CHECK-NEXT for s_cbranch_scc?

[arsenm]

Can you post an MI dump example of when this happens? It seems like this isn't something you should need to handle

[nhaehnle]

Rewrite in terms of LiveIntervals. (LivePhysRegs complains about remaining
virtual registers.)

Not sure about those DebugLocs. I'm not very familiar with their semantics,
but there isn't usually one particular instruction that can be pinned down
as the reason for inserting a new instruction (for example, when a new
instruction is added at the end of a basic block).

[nhaehnle]

WQM is needed for correctness of pixel shaders. It must be enabled for all calculations that feed into derivative calculations (explicit ones via DS and implicit ones via image sample instructions), and it must be disabled for all stores.

test/CodeGen/AMDGPU/wqm.ll

423 ↗

(On Diff #63426)

That's because I didn't actually manage to concoct a test where the pattern is unavoidable. Usually, the SCC def ends up right before the SCC use, so that the WQM instruction can just be moved around it.

I've tested the pattern with some artificial hacks in the code (in the latest version by setting First == Last in prepareInsertion).

The problem is that I cannot prove that it will never be needed. For example, it might be needed if the machine scheduler makes unusual decisions about moving store instructions between the SCC def and the SCC use.

[nhaehnle]

In D22198#482885, @arsenm wrote:

Can you post an MI dump example of when this happens? It seems like this isn't something you should need to handle

The added test case in an example (I actually encountered this out in the real world in a piglit test.)

As you can see from the excerpt at http://paste.ubuntu.com/19764805/, the most natural place to insert the s_wqm_b64 would be between the s_cmp_lt and the s_cbranch. What the new code does instead is to maintain a range of places where the s_wqm_b64 could be inserted (based on the correctness constraints for WQM), and then finds a place in that range where SCC isnt' live.

[nhaehnle]

Subsequent work revealed that there can be inconsistencies with SCC, so fix
those.

[arsenm]

include/llvm/CodeGen/LiveIntervalAnalysis.h

395–400 ↗

(On Diff #64855)

This should probably be a separate patch

lib/Target/AMDGPU/SIWholeQuadMode.cpp

531–535 ↗

(On Diff #64855)

I think this should use -1 instead of 1, and use compare != 0 to be more canonical

531–535 ↗

(On Diff #64855)

Maybe you should just emit COPY and move this expansion to copyPhysReg for scc

[nhaehnle]

• rebase
• use COPY from/to SCC for save
• separate removeRegUnit into its own patch

[nhaehnle]

It turns out that r280589 introduced a piglit regression that needs this
change to be applied already now rather than as part of later WQM rework.

I had originally planned this after D22195, but with the recent changes to
control flow lowering that other patch is currently not ready to land / be
adapted, so I adjusted this SCC fix patch so that it applies on current SVN
trunk.

[arsenm]

lib/Target/AMDGPU/SIWholeQuadMode.cpp

424 ↗

(On Diff #70365)

MI.isTransient() might be more accurate. INLINEASM for example will not be removed

[nhaehnle]

Use MI.isTransient()

[arsenm]

LGTM

llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp

bool SIInstrInfo::shouldClusterMemOps(MachineInstr &FirstLdSt,
   return (NumLoads * DstRC->getSize()) <= LoadClusterThreshold;
 }
 
 void SIInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
                               MachineBasicBlock::iterator MI,
                               const DebugLoc &DL, unsigned DestReg,
                               unsigned SrcReg, bool KillSrc) const {
 
-  // If we are trying to copy to or from SCC, there is a bug somewhere else in
-  // the backend.  While it may be theoretically possible to do this, it should
-  // never be necessary.
-  assert(DestReg != AMDGPU::SCC && SrcReg != AMDGPU::SCC);
-
   static const int16_t Sub0_15[] = {
     AMDGPU::sub0, AMDGPU::sub1, AMDGPU::sub2, AMDGPU::sub3,
     AMDGPU::sub4, AMDGPU::sub5, AMDGPU::sub6, AMDGPU::sub7,
     AMDGPU::sub8, AMDGPU::sub9, AMDGPU::sub10, AMDGPU::sub11,
     AMDGPU::sub12, AMDGPU::sub13, AMDGPU::sub14, AMDGPU::sub15,
   };
 
   static const int16_t Sub0_15_64[] = {
void SIInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
   static const int16_t Sub0_1[] = {
     AMDGPU::sub0, AMDGPU::sub1,
   };
 
   unsigned Opcode;
   ArrayRef<int16_t> SubIndices;
 
   if (AMDGPU::SReg_32RegClass.contains(DestReg)) {
+    if (SrcReg == AMDGPU::SCC) {
+      BuildMI(MBB, MI, DL, get(AMDGPU::S_CSELECT_B32), DestReg)
+          .addImm(-1)
+          .addImm(0);
+      return;
+    }
+
     assert(AMDGPU::SReg_32RegClass.contains(SrcReg));
     BuildMI(MBB, MI, DL, get(AMDGPU::S_MOV_B32), DestReg)
             .addReg(SrcReg, getKillRegState(KillSrc));
     return;
 
   } else if (AMDGPU::SReg_64RegClass.contains(DestReg)) {
     if (DestReg == AMDGPU::VCC) {
       if (AMDGPU::SReg_64RegClass.contains(SrcReg)) {
if (DestReg == AMDGPU::VCC) {
       return;
     }
 
     assert(AMDGPU::SReg_64RegClass.contains(SrcReg));
     BuildMI(MBB, MI, DL, get(AMDGPU::S_MOV_B64), DestReg)
             .addReg(SrcReg, getKillRegState(KillSrc));
     return;
 
+  } else if (DestReg == AMDGPU::SCC) {
+    assert(AMDGPU::SReg_32RegClass.contains(SrcReg));
+    BuildMI(MBB, MI, DL, get(AMDGPU::S_CMP_LG_U32))
+        .addReg(SrcReg, getKillRegState(KillSrc))
+        .addImm(0);
+    return;
   } else if (AMDGPU::SReg_128RegClass.contains(DestReg)) {
     assert(AMDGPU::SReg_128RegClass.contains(SrcReg));
     Opcode = AMDGPU::S_MOV_B64;
     SubIndices = Sub0_3_64;
 
   } else if (AMDGPU::SReg_256RegClass.contains(DestReg)) {
     assert(AMDGPU::SReg_256RegClass.contains(SrcReg));
     Opcode = AMDGPU::S_MOV_B64;

llvm/trunk/lib/Target/AMDGPU/SIWholeQuadMode.cpp

private:
   void markInstruction(MachineInstr &MI, char Flag,
                        std::vector<WorkItem> &Worklist);
   void markUsesWQM(const MachineInstr &MI, std::vector<WorkItem> &Worklist);
   char scanInstructions(MachineFunction &MF, std::vector<WorkItem> &Worklist);
   void propagateInstruction(MachineInstr &MI, std::vector<WorkItem> &Worklist);
   void propagateBlock(MachineBasicBlock &MBB, std::vector<WorkItem> &Worklist);
   char analyzeFunction(MachineFunction &MF);
 
+  bool requiresCorrectState(const MachineInstr &MI) const;
+
+  MachineBasicBlock::iterator saveSCC(MachineBasicBlock &MBB,
+                                      MachineBasicBlock::iterator Before);
+  MachineBasicBlock::iterator
+  prepareInsertion(MachineBasicBlock &MBB, MachineBasicBlock::iterator First,
+                   MachineBasicBlock::iterator Last, bool PreferLast,
+                   bool SaveSCC);
   void toExact(MachineBasicBlock &MBB, MachineBasicBlock::iterator Before,
                unsigned SaveWQM, unsigned LiveMaskReg);
   void toWQM(MachineBasicBlock &MBB, MachineBasicBlock::iterator Before,
              unsigned SavedWQM);
   void processBlock(MachineBasicBlock &MBB, unsigned LiveMaskReg, bool isEntry);
 
   void lowerLiveMaskQueries(unsigned LiveMaskReg);
 
if (WI.MI)
       propagateInstruction(*WI.MI, Worklist);
     else
       propagateBlock(*WI.MBB, Worklist);
   }
 
   return GlobalFlags;
 }
 
+/// Whether \p MI really requires the exec state computed during analysis.
+///
+/// Scalar instructions must occasionally be marked WQM for correct propagation
+/// (e.g. thread masks leading up to branches), but when it comes to actual
+/// execution, they don't care about EXEC.
+bool SIWholeQuadMode::requiresCorrectState(const MachineInstr &MI) const {
+  if (MI.isTerminator())
+    return true;
+
+  // Skip instructions that are not affected by EXEC
+  if (TII->isScalarUnit(MI))
+    return false;
+
+  // Generic instructions such as COPY will either disappear by register
+  // coalescing or be lowered to SALU or VALU instructions.
+  if (MI.isTransient()) {
+    if (MI.getNumExplicitOperands() >= 1) {
+      const MachineOperand &Op = MI.getOperand(0);
+      if (Op.isReg()) {
+        if (TRI->isSGPRReg(*MRI, Op.getReg())) {
+          // SGPR instructions are not affected by EXEC
+          return false;
+        }
+      }
+    }
+  }
+
+  return true;
+}
+
+MachineBasicBlock::iterator
+SIWholeQuadMode::saveSCC(MachineBasicBlock &MBB,
+                         MachineBasicBlock::iterator Before) {
+  unsigned SaveReg = MRI->createVirtualRegister(&AMDGPU::SReg_32RegClass);
+
+  MachineInstr *Save =
+      BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::COPY), SaveReg)
+          .addReg(AMDGPU::SCC);
+  MachineInstr *Restore =
+      BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::COPY), AMDGPU::SCC)
+          .addReg(SaveReg);
+
+  LIS->InsertMachineInstrInMaps(*Save);
+  LIS->InsertMachineInstrInMaps(*Restore);
+  LIS->createAndComputeVirtRegInterval(SaveReg);
+
+  return Restore;
+}
+
+// Return an iterator in the (inclusive) range [First, Last] at which
+// instructions can be safely inserted, keeping in mind that some of the
+// instructions we want to add necessarily clobber SCC.
+MachineBasicBlock::iterator SIWholeQuadMode::prepareInsertion(
+    MachineBasicBlock &MBB, MachineBasicBlock::iterator First,
+    MachineBasicBlock::iterator Last, bool PreferLast, bool SaveSCC) {
+  if (!SaveSCC)
+    return PreferLast ? Last : First;
+
+  LiveRange &LR = LIS->getRegUnit(*MCRegUnitIterator(AMDGPU::SCC, TRI));
+  auto MBBE = MBB.end();
+  SlotIndex FirstIdx = First != MBBE ? LIS->getInstructionIndex(*First)
+                                     : LIS->getMBBEndIdx(&MBB);
+  SlotIndex LastIdx =
+      Last != MBBE ? LIS->getInstructionIndex(*Last) : LIS->getMBBEndIdx(&MBB);
+  SlotIndex Idx = PreferLast ? LastIdx : FirstIdx;
+  const LiveRange::Segment *S;
+
+  for (;;) {
+    S = LR.getSegmentContaining(Idx);
+    if (!S)
+      break;
+
+    if (PreferLast) {
+      SlotIndex Next = S->start.getBaseIndex();
+      if (Next < FirstIdx)
+        break;
+      Idx = Next;
+    } else {
+      SlotIndex Next = S->end.getNextIndex().getBaseIndex();
+      if (Next > LastIdx)
+        break;
+      Idx = Next;
+    }
+  }
+
+  MachineBasicBlock::iterator MBBI;
+
+  if (MachineInstr *MI = LIS->getInstructionFromIndex(Idx))
+    MBBI = MI;
+  else {
+    assert(Idx == LIS->getMBBEndIdx(&MBB));
+    MBBI = MBB.end();
+  }
+
+  if (S)
+    MBBI = saveSCC(MBB, MBBI);
+
+  return MBBI;
+}
+
 void SIWholeQuadMode::toExact(MachineBasicBlock &MBB,
                               MachineBasicBlock::iterator Before,
                               unsigned SaveWQM, unsigned LiveMaskReg) {
+  MachineInstr *MI;
+
   if (SaveWQM) {
-    BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_AND_SAVEEXEC_B64),
+    MI = BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_AND_SAVEEXEC_B64),
                  SaveWQM)
              .addReg(LiveMaskReg);
   } else {
-    BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_AND_B64),
+    MI = BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_AND_B64),
                  AMDGPU::EXEC)
              .addReg(AMDGPU::EXEC)
              .addReg(LiveMaskReg);
   }
+
+  LIS->InsertMachineInstrInMaps(*MI);
 }
 
 void SIWholeQuadMode::toWQM(MachineBasicBlock &MBB,
                             MachineBasicBlock::iterator Before,
                             unsigned SavedWQM) {
+  MachineInstr *MI;
+
   if (SavedWQM) {
-    BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::COPY), AMDGPU::EXEC)
+    MI = BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::COPY), AMDGPU::EXEC)
              .addReg(SavedWQM);
   } else {
-    BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_WQM_B64),
+    MI = BuildMI(MBB, Before, DebugLoc(), TII->get(AMDGPU::S_WQM_B64),
                  AMDGPU::EXEC)
              .addReg(AMDGPU::EXEC);
   }
+
+  LIS->InsertMachineInstrInMaps(*MI);
 }
 
 void SIWholeQuadMode::processBlock(MachineBasicBlock &MBB, unsigned LiveMaskReg,
                                    bool isEntry) {
   auto BII = Blocks.find(&MBB);
   if (BII == Blocks.end())
     return;
 
   const BlockInfo &BI = BII->second;
 
   if (!(BI.InNeeds & StateWQM))
     return;
 
   // This is a non-entry block that is WQM throughout, so no need to do
   // anything.
   if (!isEntry && !(BI.Needs & StateExact) && BI.OutNeeds != StateExact)
     return;
 
   DEBUG(dbgs() << "\nProcessing block BB#" << MBB.getNumber() << ":\n");
 
   unsigned SavedWQMReg = 0;
   bool WQMFromExec = isEntry;
   char State = isEntry ? StateExact : StateWQM;
-  MachineInstr *FirstNonWQM = nullptr;
 
   auto II = MBB.getFirstNonPHI(), IE = MBB.end();
-  while (II != IE) {
-    MachineInstr &MI = *II;
-    ++II;
+  if (isEntry)
+    ++II; // Skip the instruction that saves LiveMask
 
-    // Skip instructions that are not affected by EXEC
-    if (TII->isScalarUnit(MI) && !MI.isTerminator())
-      continue;
+  MachineBasicBlock::iterator First = IE;
+  for (;;) {
+    MachineBasicBlock::iterator Next = II;
+    char Needs = 0;
+    char OutNeeds = 0;
 
-    // Generic instructions such as COPY will either disappear by register
-    // coalescing or be lowered to SALU or VALU instructions.
-    if (TargetInstrInfo::isGenericOpcode(MI.getOpcode())) {
-      if (MI.getNumExplicitOperands() >= 1) {
-        const MachineOperand &Op = MI.getOperand(0);
-        if (Op.isReg()) {
-          if (TRI->isSGPRReg(*MRI, Op.getReg())) {
-            // SGPR instructions are not affected by EXEC
-            continue;
-          }
+    if (First == IE)
+      First = II;
+
+    if (II != IE) {
+      MachineInstr &MI = *II;
+
+      if (requiresCorrectState(MI)) {
+        auto III = Instructions.find(&MI);
+        if (III != Instructions.end()) {
+          Needs = III->second.Needs;
+          OutNeeds = III->second.OutNeeds;
         }
       }
+
+      if (MI.isTerminator() && !Needs && OutNeeds == StateExact)
+        Needs = StateExact;
+
+      if (MI.getOpcode() == AMDGPU::SI_ELSE && BI.OutNeeds == StateExact)
+        MI.getOperand(3).setImm(1);
+
+      ++Next;
+    } else {
+      // End of basic block
+      if (BI.OutNeeds & StateWQM)
+        Needs = StateWQM;
+      else if (BI.OutNeeds == StateExact)
+        Needs = StateExact;
     }
 
-    char Needs = 0;
-    char OutNeeds = 0;
-    auto InstrInfoIt = Instructions.find(&MI);
-    if (InstrInfoIt != Instructions.end()) {
-      Needs = InstrInfoIt->second.Needs;
-      OutNeeds = InstrInfoIt->second.OutNeeds;
-    }
-
-    // Keep track of the first consecutive non-WQM instruction, so that we
-    // switch away from WQM as soon as possible, potentially saving a small
-    // bit of bandwidth on loads.
-    if (Needs == StateWQM)
-      FirstNonWQM = nullptr;
-    else if (!FirstNonWQM)
-      FirstNonWQM = &MI;
+    if (Needs) {
+      if (Needs != State) {
+        MachineBasicBlock::iterator Before =
+            prepareInsertion(MBB, First, II, Needs == StateWQM,
+                             Needs == StateExact || WQMFromExec);
 
-    // State switching
-    if (Needs && State != Needs) {
         if (Needs == StateExact) {
-        assert(!SavedWQMReg);
-
           if (!WQMFromExec && (OutNeeds & StateWQM))
             SavedWQMReg = MRI->createVirtualRegister(&AMDGPU::SReg_64RegClass);
 
-        toExact(MBB, FirstNonWQM, SavedWQMReg, LiveMaskReg);
+          toExact(MBB, Before, SavedWQMReg, LiveMaskReg);
         } else {
           assert(WQMFromExec == (SavedWQMReg == 0));
-        toWQM(MBB, &MI, SavedWQMReg);
+
+          toWQM(MBB, Before, SavedWQMReg);
+
+          if (SavedWQMReg) {
+            LIS->createAndComputeVirtRegInterval(SavedWQMReg);
             SavedWQMReg = 0;
           }
+        }
 
         State = Needs;
       }
 
-    if (MI.getOpcode() == AMDGPU::SI_ELSE && BI.OutNeeds == StateExact)
-      MI.getOperand(3).setImm(1);
+      First = IE;
     }
 
-  if ((BI.OutNeeds & StateWQM) && State != StateWQM) {
-    assert(WQMFromExec == (SavedWQMReg == 0));
-    toWQM(MBB, MBB.end(), SavedWQMReg);
-  } else if (BI.OutNeeds == StateExact && State != StateExact) {
-    toExact(MBB, FirstNonWQM ? MachineBasicBlock::iterator(FirstNonWQM)
-                             : MBB.getFirstTerminator(),
-            0, LiveMaskReg);
+    if (II == IE)
+      break;
+    II = Next;
   }
 }
 
 void SIWholeQuadMode::lowerLiveMaskQueries(unsigned LiveMaskReg) {
   for (MachineInstr *MI : LiveMaskQueries) {
     const DebugLoc &DL = MI->getDebugLoc();
     unsigned Dest = MI->getOperand(0).getReg();
+    MachineInstr *Copy =
         BuildMI(*MI->getParent(), MI, DL, TII->get(AMDGPU::COPY), Dest)
             .addReg(LiveMaskReg);
+
+    LIS->ReplaceMachineInstrInMaps(*MI, *Copy);
     MI->eraseFromParent();
   }
 }
 
 bool SIWholeQuadMode::runOnMachineFunction(MachineFunction &MF) {
   if (MF.getFunction()->getCallingConv() != CallingConv::AMDGPU_PS)
     return false;
 
bool SIWholeQuadMode::runOnMachineFunction(MachineFunction &MF) {
   // Store a copy of the original live mask when required
   unsigned LiveMaskReg = 0;
   {
     MachineBasicBlock &Entry = MF.front();
     MachineBasicBlock::iterator EntryMI = Entry.getFirstNonPHI();
 
     if (GlobalFlags & StateExact || !LiveMaskQueries.empty()) {
       LiveMaskReg = MRI->createVirtualRegister(&AMDGPU::SReg_64RegClass);
-      BuildMI(Entry, EntryMI, DebugLoc(), TII->get(AMDGPU::COPY), LiveMaskReg)
+      MachineInstr *MI = BuildMI(Entry, EntryMI, DebugLoc(),
+                                 TII->get(AMDGPU::COPY), LiveMaskReg)
                              .addReg(AMDGPU::EXEC);
+      LIS->InsertMachineInstrInMaps(*MI);
     }
 
     if (GlobalFlags == StateWQM) {
       // For a shader that needs only WQM, we can just set it once.
       BuildMI(Entry, EntryMI, DebugLoc(), TII->get(AMDGPU::S_WQM_B64),
               AMDGPU::EXEC)
           .addReg(AMDGPU::EXEC);
 
       lowerLiveMaskQueries(LiveMaskReg);
       // EntryMI may become invalid here
       return true;
     }
   }
 
   DEBUG(printInfo());
 
   lowerLiveMaskQueries(LiveMaskReg);
 
   // Handle the general case
   for (auto BII : Blocks)
     processBlock(*BII.first, LiveMaskReg, BII.first == &*MF.begin());
 
+  // Physical registers like SCC aren't tracked by default anyway, so just
+  // removing the ranges we computed is the simplest option for maintaining
+  // the analysis results.
+  LIS->removeRegUnit(*MCRegUnitIterator(AMDGPU::SCC, TRI));
+
   return true;
 }

llvm/trunk/test/CodeGen/AMDGPU/wqm.ll

 if:
   store volatile <4 x float> %dtex, <4 x float>* undef
   unreachable
 
 else:
   ret <4 x float> %dtex
 }
 
+; Test awareness that s_wqm_b64 clobbers SCC.
+;
+; CHECK-LABEL: {{^}}test_scc:
+; CHECK: s_mov_b64 [[ORIG:s\[[0-9]+:[0-9]+\]]], exec
+; CHECK: s_wqm_b64 exec, exec
+; CHECK: s_cmp_
+; CHECK-NEXT: s_cbranch_scc
+; CHECK: ; %if
+; CHECK: s_and_b64 exec, exec, [[ORIG]]
+; CHECK: image_sample
+; CHECK: ; %else
+; CHECK: s_and_b64 exec, exec, [[ORIG]]
+; CHECK: image_sample
+; CHECK: ; %end
+define amdgpu_ps <4 x float> @test_scc(i32 inreg %sel, i32 %idx) #1 {
+main_body:
+  %cc = icmp sgt i32 %sel, 0
+  br i1 %cc, label %if, label %else
+
+if:
+  %r.if = call <4 x float> @llvm.SI.image.sample.i32(i32 0, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+  br label %end
+
+else:
+  %r.else = call <4 x float> @llvm.SI.image.sample.v2i32(<2 x i32> <i32 0, i32 1>, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+  br label %end
+
+end:
+  %r = phi <4 x float> [ %r.if, %if ], [ %r.else, %else ]
+
+  call void @llvm.amdgcn.buffer.store.f32(float 1.0, <4 x i32> undef, i32 %idx, i32 0, i1 0, i1 0)
+
+  ret <4 x float> %r
+}
+
+
 declare void @llvm.amdgcn.image.store.v4i32(<4 x float>, <4 x i32>, <8 x i32>, i32, i1, i1, i1, i1) #1
 declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) #1
 declare void @llvm.amdgcn.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i1, i1) #1
 
 declare <4 x float> @llvm.amdgcn.image.load.v4i32(<4 x i32>, <8 x i32>, i32, i1, i1, i1, i1) #2
 declare float @llvm.amdgcn.buffer.load.f32(<4 x i32>, i32, i32, i1, i1) #2
 
 declare <4 x float> @llvm.SI.image.sample.i32(i32, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #3
+declare <4 x float> @llvm.SI.image.sample.v2i32(<2 x i32>, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #3
 declare <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32>, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #3
 
 declare void @llvm.AMDGPU.kill(float)
 declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
 
 attributes #1 = { nounwind }
 attributes #2 = { nounwind readonly }
 attributes #3 = { nounwind readnone }
 attributes #4 = { "amdgpu-ps-wqm-outputs" }